<?xml version="1.0" encoding="UTF-8"?>
<record
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd"
    xmlns="http://www.loc.gov/MARC21/slim">

  <leader>02294nam a2200253 i 4500</leader>
  <controlfield tag="001">UUN-OA-637</controlfield>
  <controlfield tag="005">20260922220311.0</controlfield>
  <datafield tag="020" ind1=" " ind2=" ">
    <subfield code="a">9783961100903</subfield>
  </datafield>
  <datafield tag="100" ind1="1" ind2=" ">
    <subfield code="a">Steven Moran</subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="0">
    <subfield code="a">The Unicode cookbook for linguists: Managing writing systems using orthography profiles</subfield>
  </datafield>
  <datafield tag="264" ind1=" " ind2="1">
    <subfield code="b">Language Science Press</subfield>
    <subfield code="c">2018</subfield>
  </datafield>
  <datafield tag="300" ind1=" " ind2=" ">
    <subfield code="a">1 online resource</subfield>
  </datafield>
  <datafield tag="336" ind1=" " ind2=" ">
    <subfield code="a">text</subfield>
    <subfield code="b">txt</subfield>
    <subfield code="2">rdacontent</subfield>
  </datafield>
  <datafield tag="337" ind1=" " ind2=" ">
    <subfield code="a">computer</subfield>
    <subfield code="b">c</subfield>
    <subfield code="2">rdamedia</subfield>
  </datafield>
  <datafield tag="338" ind1=" " ind2=" ">
    <subfield code="a">online resource</subfield>
    <subfield code="b">cr</subfield>
    <subfield code="2">rdacarrier</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">This text is a practical guide for linguists, and programmers, who work with data in multilingual computational environments. We introduce the basic concepts needed to understand how writing systems and character encodings function, and how they work together at the intersection between the Unicode Standard and the International Phonetic Alphabet. Although these standards are often met with frustration by users, they nevertheless provide language researchers and programmers with a consistent computational architecture needed to process, publish and analyze lexical data from the world's languages. Thus we bring to light common, but not always transparent, pitfalls which researchers face when working with Unicode and IPA. Having identified and overcome these pitfalls involved in making writing systems and character encodings syntactically and semantically interoperable (to the extent that they can be), we created a suite of open-source Python and R tools to work with languages using orthography profiles that describe author- or document-specific orthographic conventions. In this cookbook we describe a formal specification of orthography profiles and provide recipes using open source tools to show how users can segment text, analyze it, identify errors, and to transform it into different written forms for comparative linguistics research.</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">Computer Science</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">Humanities - Linguistics</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">B. Sc. Artificial Intelligence</subfield>
    <subfield code="2">local</subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="4">
    <subfield code="a">B. Sc. Cyber Security</subfield>
    <subfield code="2">local</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Attribution</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2="0">
    <subfield code="u">https://langsci-press.org/catalog/book/176</subfield>
    <subfield code="y">Read online</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2="2">
    <subfield code="u">https://open.umn.edu/opentextbooks/textbooks/the-unicode-cookbook-for-linguists-managing-writing-systems-using-orthography-profiles</subfield>
    <subfield code="y">Open Textbook Library record</subfield>
  </datafield>
  <datafield tag="999" ind1=" " ind2=" ">
    <subfield code="c">340</subfield>
    <subfield code="d">340</subfield>
  </datafield>
</record>
